[논문]CNN기반 굴삭기용 부하 측정 시스템 구현을 위한 연구

정황훈; 신영일; 이진호; 조기용

doi:10.7839/ksfc.2023.20.4.133

CNN기반 굴삭기용 부하 측정 시스템 구현을 위한 연구
A Study of Weighing System to Apply into Hydraulic Excavator with CNN 원문보기

드라이브ㆍ컨트롤 = Journal of drive and control, v.20 no.4, 2023년, pp.133 - 139

정황훈 (Intelligent Control Lab., Korea Construction Equipment Technology Institute) , 신영일 (Intelligent Control Lab., Korea Construction Equipment Technology Institute) , 이진호 (Intelligent Control Lab., Korea Construction Equipment Technology Institute) , 조기용 (Intelligent Control Lab., Korea Construction Equipment Technology Institute)

Abstract ▼ AI-Helper

A weighing system calculates the bucket's excavation amount of an excavator. Usually, the excavation amount is computed by the excavator's motion equations with sensing data. But these motion equations have computing errors that are induced by assumptions to the linear systems and identification of the equation's parameters. To reduce computing errors, some commercial weighing system incorporates particular motion into the excavation process. This study introduces a linear regression model on an artificial neural network that has fewer predicted errors and doesn't need a particular pose during an excavation. Time serial data were gathered from a 30tons excavator's loading test. Then these data were preprocessed to be adjusted by MPL (Multi Layer Perceptron) or CNN (Convolutional Neural Network) based linear regression models. Each model was trained by changing hyperparameter such as layer or node numbers, drop-out rate, and kernel size. Finally ID-CNN-based linear regression model was selected.

주제어

표/그림 (12)

그림 Fig. 1 Sandbag for test's payload
그림 Fig. 2 Test data on a dumping process with payload variation
표 Table 1 Sensor specification
표 Table 2 A specification of dataset's shape
그림 Fig. 3 Learning results for linear and polynomial regression
그림 Fig. 4 Predicted results on validation dataset
그림 Fig. 5 Predicted result's error on test dataset (polynomial regression)
표 Table 4 Simulation results of weighing system
표 Table 3 A specification of hyperparameter
그림 Fig. 6 Predicted results error on validation dataset
그림 Fig. 7 Predicted result's error on test dataset (min. and max. error)
그림 Fig. 8 Predicted result's error on test dataset (min. and max. error rate)

참고문헌 (15)

K. W. Park, Y. J. Park and G. B. Jang, "Deep Learning-based Excavation Weighing System with Mitigated Driver Bias", KSAE Spring Conference Proceedings, pp.1210-1215, 2023？
M. S. Lee, Y. I. Shin, S. J. Choi, J. W. Kwon and K. Y. Choi, "Development of Load Weighing Algorithm for Excavator", KSAE Annual Conference Proceedings, pp.123-456, 2011.？
M. K. Seo, H. Y. Shin, H. Y. Lee, J. I. Ko and E. Tumrnjargal, "Development of Onboard Scales to Measure the Weight of Trucks", J. of Drive and Control, Vol.18, No.1, pp.9-16, 2021.？
D. Y. Shin, "A Study on Excavation Path Design of Excavator Considering Motion Limits", J. of Drive and Control, Vol.18, No.2, pp.20-31, 2021.？
J. Cho, S. Na, M. Kim and M. Park, "Development of a Workload Index for Monitoring Durability Test of an Excavator", J. of Drive and Control, Vol.19, No.4, pp.29-35, 2022.？
Caterpillar, Cat Payload for Excavator, https://www.cat.com/en_US/by-industry/construction-industry-resources/technology/payload.html, 2023.？
Trimble, Trimble LOADRITE Payload Management for Trimble Earthworks Grade Control Platform Datasheet-English, https://heavyindustry.trible.com/resources/datasheet-brochures-english/trimble-loadrite-payload-management-for-trimble-earthworks-grade-control-platform-english, 2023.？
H. H. Jeong, M. S. Lee and Y. I. Shin, "A Study of a Hydraulic Excavator's Test to Verify of Payload Estimation by Bucket's Motion Equation", J. of Drive and Control, Vol.19, No.2, pp.11-16, 2022.？
N. Bennett, A. Walawalkar and C. Schindler, "Payload Estimation in Excavators : Model- Based Evaluation and Comparison of Current Payload Estimation Systems" CVT 2014 3rd Commercial Vehicle Technology Symposium, Vol.3, pp.1-14, 2014.？
A. Bewley, R. Shekhar, S. Leonard, B. Upcroft and P. Lever, "Real-time volume estimation of a dragline payload", 2011 IEEE International Conference on Robotics and Automation (ICRA), Vol.3, pp. 1571-1576, 2011.？
A. Gawlik and P. Kucybala, "Dynamic Weighing System used in Excavator," J. of KONES Powertrain and Transport, Vol.24, No.4, pp.31-38, 2017.？
Q. Liu and C. Huang, "A Fault Diagnosis Method Based on Transfer Convolutional Neural Networks," in IEEE Access, vol. 7, pp. 171423-171430, 2019.？

상세보기
D. Li, J. Zhang, Q. Zhang and X. Wei, "Classification of ECG signals based on 1D convolution neural network," 2017 IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom), pp. 1-6, 2017.？
E. Ostertagova, "Modelling using Polynomial Regression", Procedia Engineering, Vol. 48, pp. 500-506, 2012.？

상세보기
J. Hindman, R. Burton and G. Schoenau, "An Artificial Neural Network Approach to Payload Estimation in Four Wheel Drive Loaders," 2007 ASME International Mechanical Engineering Congress and Exposition, pp.1-5, 2007.

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증